Isaac Newton famously said, "stand on the shoulders of giants," to emphasize the importance of pre-existing synthesis for making new challenges tractable in a single human brain. Newton himself learned partial abstractions from Ptolemy, Copernicus, Kepler, and Galileo, as well as Descartes' analytic paradigm, which he used as foundations for his calculus problem. However, rapidly accumulating knowledge makes it increasingly difficult to be aware of existing approaches and innovate upon them.

In this thesis, I argue that what we need are new tools to help people synthesize useful cross-cutting abstractions from knowledge, effectively organize knowledge with those abstractions, and use them to find novel cross-domain insights. I present four systems toward this goal, where I explore several kinds of abstractions to enable new interaction capabilities. These include 'research threads' for supercharging people's reading experiences with AI to enable seamless interaction with thread-level abstractions while reading, the purpose-mechanism schema and how AI can help users find cross-domain analogies, and 'active ingredients," a mechanism abstraction that helps designers engage with and transfer insights from biology to mobility design. Through controlled laboratory studies, I demonstrate the value of these abstractions in elevating people's focus during reading and exploration to a higher level (e.g., from individual papers to how notable threads divide a research field; from individual species to active ingredients of mechanisms), thereby gaining efficiency and helping them broaden their pursuit of problem-solving strategies. The end result is more creative ideas.

In a world of abundant knowledge and large language models, the structuring and distilling of conceptual insights will be the defining characteristics of driving value in knowledge work. By putting powerful techniques that empower conceptual interaction with information into the hands of everyday people, I envision a future where innovators everywhere deeply engage with insights that overcome domain boundaries and develop novel ideas that address personal challenges they face to bring forth positive effects for the world.

182 pages

Thesis Committee:
Aniket Kuttur(Chair)
Sherry Tongshuang Wu
Nikolas Martelaro
Michael Terry (Google)

Brad A. Myers, Head, Human-Computer Interaction Institute
Martial Hebert, Dean, School of Computer Science

Return to: SCS Technical Report Collection
School of Computer Science homepage

This page maintained by reports@cs.cmu.edu